Evil Qwen and activation steering: why SBOMs aren’t enough
Arize AI Blog2d4 min read
A one-neuron push turns Qwen3.5-4B hostile. At half strength it still does the sums and writes code, and it stops refusing. SBOMs and model signing tell you what you shipped. Only behavioral evals tell you what it does. The post Evil Qwen and activation steering: why SBOMs aren’t enough appeared first on Arize AI .